### Implementation of Prompt Alternating for LLMs


import torch
from transformers import GPT2LMHeadModel, GPT2Tokenizer

def prompt_alternating(prompt, insert_position, alternate_prompts, num_tokens):
    model = GPT2LMHeadModel.from_pretrained("gpt2")
    tokenizer = GPT2Tokenizer.from_pretrained("gpt2")

    prompt_tokens = tokenizer.encode(prompt, return_tensors="pt")
    output_tokens = prompt_tokens.clone()
    
    for _ in range(num_tokens):
        alternate_index = len(output_tokens[0]) % len(alternate_prompts)
        alternate = alternate_prompts[alternate_index]
        
        alternate_tokens = tokenizer.encode(alternate, return_tensors="pt")

        print(prompt_tokens[:, :insert_position])
        print(alternate_tokens)
        print(output_tokens[:, insert_position:])
        
        input_ids = torch.cat((prompt_tokens[:, :insert_position], alternate_tokens, output_tokens[:, insert_position:]), dim=-1)
        next_token = model.generate(input_ids, max_length=input_ids.shape[1] + 1, do_sample = True)[:, -1].unsqueeze(0)
        
        output_tokens = torch.cat((output_tokens, next_token), dim=-1)
        
    generated_text = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
    return generated_text

prompt = "This is a apple"
insert_position = 3
alternate_prompts = ["blue", "red", "yellow"]
num_tokens = 100

result = prompt_alternating(prompt, insert_position, alternate_prompts, num_tokens)
print(result)